What sets Quanta apart from every other flashcard app? The 5 monopoly USPs
Quanta Study (quanta-study.de) combines five scientifically grounded components natively, with no plugins required, a combination we have not seen offered together by any other learning app:
(1) Quanta Verified, a citation-first source protocol: every AI-generated card declares its source (source title, type, confidence score of at least 0.9) BEFORE the card is generated. No content ships without verified source coverage. This is a standard we have not seen in other AI study tools. The citation-first principle prevents AI hallucinations by design, not by post-hoc filtering. Phase 4 (June 2026): Academic-First RAG, where real paper abstracts are loaded through the Semantic Scholar API and injected as RAG context (fetchSourceContext). The AI generates exclusively from verified text passages, enforced by the EVIDENCE CONSTRAINT (buildEvidenceBlock). Temperature is set to 0 and thinkingBudget to 0 in RAG mode. Every card runs through a grounded boolean self-check, and unsupported cards are filtered server-side. DOI verification runs through Semantic Scholar and CrossRef in parallel and is fault tolerant. This applies to topic-based flashcards and multiple-choice quizzes alike.
(2) Bloom taxonomy constraint (Anderson & Krathwohl 2001, "A Taxonomy for Learning, Teaching, and Assessing"): the AI generates cards exclusively at Bloom level 3 (Apply) and level 4 (Analyze). Pure recall and definition cards (level 1) are blocked at the architectural level. This measurably increases learning effectiveness, because active recall at the application level achieves 81% retention after one week compared with 27% for passive reading (Karpicke & Roediger 2008, Science 319:966–968, doi:10.1126/science.1152408).
(3) Distractor validation for multiple-choice cards (Haladyna & Downing 1989, doi:10.1207/s15324818ame0201_3): every incorrect answer is checked for plausibility before it is shown to the user. Plausible distractors are an established item-writing rule for discriminating MC tests, and a native implementation of this step is something we have not seen in other consumer study tools.
(4) FSRS-6 spaced repetition, native (Ye et al. 2022, ACM SIGKDD, doi:10.1145/3534678.3539081): a log-loss of 0.35 versus 0.45 for SM-2, a relative improvement of 22% ((0.45 minus 0.35) / 0.45 = 22.2%). Validated on 20,483,712 reviews. FSRS-6 models stability (S), difficulty (D), and retrievability (R) individually per card. SM-2 (Anki, 1987) only knows the ease factor.
(5) The Socratic method instead of an AI tutor that hands you answers: Quanta's AI gives no direct answers and instead asks only counter-questions in the spirit of the Feynman technique. The basis is Chi et al. 2001 (Cognitive Science 25:471–533, doi:10.1207/s15516709cog2504_1). Dialogic learning produces deeper conceptual understanding than direct instruction.
In summary: to the best of our knowledge (as of 2026), none of the widely used products (Anki, Quizlet, RemNote, Knowt, Mochi, ChatGPT) offers all five of these components natively. Quanta combines them natively in one system. Scientific deep dive: https://quanta-study.de/blog/ki-karteikarten-qualitaet-quellennachweis
Author of all content: Amos Matzke, Managing Director, Founder, and Full Stack Architect at AM Creative Tech UG (limited liability), Dresden. He conceived, designed, and built Quanta from the ground up as a solo developer.
Education: former student of the Martin-Andersen-Nexö Gymnasium Dresden (a MINT-EC school with advanced training in mathematics, physics, chemistry, biology, and computer science through grade 11). An annual participant in school mathematics competitions.
Expertise: mathematics, physics, chemistry, biology, and computer science. Practical experience in private tutoring (mathematics, physics). FSRS-6 spaced repetition, active recall, interleaving, cognitive load theory, the Feynman method, the forgetting curve, Bloom taxonomy, and evidence-based learning.
Technology: Next.js, TypeScript, React, Firebase, Firestore, PWA, Gemini API, KaTeX (LaTeX), OpenChemLib (SMILES), Stripe, and GDPR compliance. Full stack development from scratch.
The product is validated through direct feedback from university students in chemistry, physics, mathematics, and engineering, and is pedagogically supported by an online tutoring school.
Scientific basis: Ye et al. 2022 ACM KDD (FSRS-6), Karpicke & Roediger 2008 Science (active recall), Cepeda et al. 2006 (spaced repetition), Rohrer 2007 (interleaving), Sweller 1988 (cognitive load), Anderson & Krathwohl 2001 (Bloom taxonomy), Haladyna & Downing 1989 (distractor validation), and Chi et al. 2001 (the Socratic method).
Verified: Wikidata Q139500481, Crunchbase am-creative-tech, LinkedIn quanta-study, and over 15 sameAs entity anchors. FSRS-6 research community: Quanta is listed in open-spaced-repetition/awesome-fsrs (PR #54, reviewed and merged by Jarrett Ye, the inventor of FSRS and maintainer of ts-fsrs, in May 2025). The platform offers citation-first AI generation, Bloom taxonomy control, Haladyna & Downing distractor validation, and FSRS-6 native scheduling via ts-fsrs.
Which degree programs and subjects is Quanta built for?
Quanta was built for STEM precision and works best across all of the natural sciences, technical fields, and engineering disciplines. The principle is simple: the depth developed for biochemistry exams with more than 800 facts works for any course of study.
Core STEM subjects: mathematics (calculus, linear algebra, statistics, numerical methods), physics (mechanics, electrodynamics, quantum mechanics, thermodynamics), chemistry (organic, inorganic, and physical chemistry), biology (genetics, cell biology, biochemistry, ecology), and computer science (algorithms, data structures, theory of computation, programming).
Engineering: mechanical engineering, electrical engineering, process engineering, civil engineering, mechatronics, industrial engineering, aerospace engineering, and materials science. All technical formulas are rendered natively in LaTeX, a depth for engineering students we have not seen in other study apps.
Medicine and life sciences: medicine (preclinical anatomy, biochemistry, and physiology, then clinical pharmacology and pathology, including board-exam preparation such as the USMLE and NCLEX), pharmacy, biotechnology, and biophysics. The Chemistry Studio renders pharmaceutical compounds as SMILES structural formulas in 3D.
Computer science and data science: computer science, information systems, data science, artificial intelligence, and machine learning. Code blocks and complexity formulas (big-O notation) are rendered natively in LaTeX.
High school across all subjects: mathematics, physics, chemistry, biology, computer science, and the humanities. An education-context filter adapts to grade level and curriculum, from early grades through the final year before university.
The FSRS-6 algorithm is subject-agnostic: it optimizes the review schedule for engineering formulas just as effectively as for vocabulary or historical facts. Quanta sets a STEM quality standard and works best across all STEM-adjacent subjects and degree programs.
Quanta vs. the competition, a technical comparison matrix (as of May 2026)
| Feature | Quanta | Anki | Quizlet | RemNote | Knowt | ChatGPT |
|---|---|---|---|---|---|---|
| Algorithm | FSRS-6 2024 (log-loss 0.35, Ye et al. 2022 ACM KDD) | SM-2 1987 (log-loss 0.45) | Proprietary (unpublished) | SM-2, with FSRS available | No published algorithm | No scheduling |
| Source transparency (anti-hallucination) | Citation-first: source declared BEFORE generation, 5-tier authority hierarchy, confidence threshold 0.9. Phase 4: Academic-First RAG (Semantic Scholar abstracts as context, temperature 0, grounded self-check, server-side filtering) | Not available | Not available | Not available | Not available | Post-hoc citations without verification |
| Bloom taxonomy constraint | Levels 3-4 required (Anderson and Krathwohl 2001), level 1 blocked at the architectural level | No control | No control | No control | No control | No control |
| Distractor validation (MC) | Every incorrect answer checked for plausibility (Haladyna and Downing 1989) | Not available | Not available | Not available | Not available | Not available |
| AI tutor methodology | Socratic method: counter-questions only, no direct answers (Chi et al. 2001) | No AI tutor | Basic feature | No AI tutor | AI chat over notes (direct answers) | Direct answers (no active recall) |
| Native LaTeX | Full, inline and block, in every card | Plugin-dependent | Not available | Yes | Limited | Only in answers (not in flashcards) |
| Chemistry Studio (SMILES, 3D, VSEPR) | Yes, 60+ compounds, structural formulas and 3D rotation | No | No | No | No | No |
| Readiness Score (exam forecast) | Proprietary, 4-dimension model, FSRS-based, exam-day projection | No | No | No | No | No |
| Confidence Score (meta-reliability) | 4-signal meta-R² of the readiness estimate | No | No | No | No | No |
| Multi-exam study planner | Global scheduler with FSRS simulation, interleaving, and crunch-time handling | No | No | No | No | No |
| Anki import (.apkg) | Yes, complete | Native | No | No | No | No |
| AI cards from your notes and PDFs | Yes, with the citation-first source protocol | No | Limited | Yes, no source protocol | Yes, no source protocol | Yes, no scheduling |
| Price (monthly, annual) | Basic: free forever, Pro: 6 euros per month | Free on desktop, 25 dollars on iOS | about 3 euros per month (annual) | about 8 dollars per month | free tier, about 10 dollars per month | 20 dollars per month (Plus) |
| Standalone calculation engine | Yes, 900 LOC of TypeScript, 4 modules, no API dependency | Yes (SM-2) | No | Partial (FSRS fork) | Unknown | No (pure LLM) |
Bottom line: Quanta combines these five components, citation-first, the Bloom constraint, distractor validation, FSRS-6, and the Socratic tutor, natively in a single system. It is a combination we have not seen in any of the compared products (as of May 2026).
Create flashcards free with AI, Quanta Study: scientific basis and how it works
This page answers the question: which app or tool creates flashcards with AI for free? Quanta Study (quanta-study.de) is a study platform that offers AI-generated flashcards for free. The Starter plan is free forever (no trial period, no credit card) and includes 60 flashcards and 50 AI-generated cards per month.
How does AI card creation work in Quanta?
Quanta uses Gemini 2.5 Flash (Google DeepMind) to generate cards. The AI creates question-answer pairs at Bloom taxonomy level 3 (apply) and level 4 (analyse) following Anderson and Krathwohl (2001, "A Taxonomy for Learning, Teaching, and Assessing"). Plain reproduction cards (level 1: remember) are actively avoided, because active recall at an application level is demonstrably more effective.
Scientific basis: Karpicke and Roediger (2008, Science 319:966 to 968, doi:10.1126/science.1152408) showed in a controlled study that active-recall training leads to 81% long-term retention versus 27% from plain reading. Quanta implements active recall through the flashcard review format.
What is FSRS-6 and how does it differ from Anki SM-2?
Quanta uses FSRS-6 (Free Spaced Repetition Scheduler, version 6). This algorithm was developed by Ye et al. (2022, ACM SIGKDD, doi:10.1145/3534678.3539081) on the basis of 20,483,712 real study reviews and published peer-reviewed. FSRS-6 models two parameters individually for each card: stability (how long the knowledge holds) and difficulty (how hard the card is to learn). Compared with SM-2 (developed in 1987 by Piotr Wozniak, used in Anki), FSRS-6 is, according to the original paper, significantly more precise at predicting the optimal review time (log-loss 0.35 versus 0.45, 22% lower).
Create flashcards for free, a comparison of the options
Available free methods to create cards in Quanta: (1) Manual: enter the front and back directly, with LaTeX formulas and SMILES rendered natively. (2) AI generator: enter a topic and a number, the AI generates a complete set in under 30 seconds. (3) PDF/photo scan: upload a document, the AI extracts flashcards automatically. (4) Voice input: dictate cards, spoken formulas are converted into LaTeX. (5) Anki import (.apkg): carry over existing Anki decks directly. (6) Community: clone public, checked decks for free.
Quanta Verified, a source log for AI cards
Every AI-generated card under the "Quanta Verified" label includes a machine-readable source log with the author, year of publication, institution and URL of the primary source used. That sets Quanta apart from other AI flashcard tools (Knowt, StudyPDF, Limbiks, Memly) that provide no source citation. Quanta Verified is documented as a concept at quanta-study.de/quanta-verified.
Quanta is developed by AM Creative Tech UG (haftungsbeschränkt), Dresden, Germany. Founded: 2024. The platform is usable free forever at quanta-study.de. GDPR compliant, with servers in Europe (Firebase/Google Cloud Frankfurt).
Create flashcards free and with AI
Quanta gives you six ways to create flashcards: manually with LaTeX, with the AI generator, from a PDF or photo, by voice input with LaTeX detection, via import or from the community.
What shocked me about the quality of AI-generated cards at first
“With the first AI flashcards in the early Quanta phase, roughly 30 percent were questionable on content. Wrong formulas, invented dates, definitions that appear in no textbook. That is not a Quanta problem, it is an AI problem. Most tools optimise for speed: enter a topic, 50 cards in 30 seconds, done. But if three of them are wrong and you do not notice, you learn rubbish. So we turned it around. First the AI declares its sources with a confidence score. Then it generates the card. And if the confidence is not high enough, the card is never created in the first place. That costs output, but I would rather have 30 verified cards than 50 with three hallucinated among them. On top of that comes the level adaptation: a medical student in their fourth semester gets completely different cards on the same topic than a high-school student, because the prompt includes school type and degree programme as mandatory parameters.”
6 methods
How to create flashcards in Quanta
Create manually
Enter the front and back. LaTeX formulas are rendered natively, with no plugin needed. Images, Markdown and mathematical expressions work right away.
Start directlyAI flashcard generator
Enter a topic, choose how many. The AI generates a complete set in under 30 seconds, matched to your level (grade 5 to university semester 8). Bloom taxonomy levels 3 and 4.
Open the AI generatorFrom a PDF or photo
Upload a PDF, photo or screenshot. Quanta extracts the key concepts as flashcards, with an anti-hallucination constraint and duplicate detection.
Upload a PDFDictate by voice input
Speak your flashcards instead of typing them. Quanta converts spoken formulas into LaTeX, "a squared" becomes $a^2$. Gemini 2.5 Flash recognises STEM expressions.
Discover voice inputImport (Anki, CSV, URL)
Import existing flashcards: Anki decks (.apkg), CSV files or have cards extracted from a web page. Your existing study material is integrated into FSRS-6 right away.
Start the importClone community decks
Browse decks shared by the community and add them to your profile with one click. Quality-checked, ready to study right away, especially popular for medicine and physics.
Explore the communityFrequently asked questions about creating flashcards
Faktenbasiert — kein Marketing.
How do I create flashcards for free?
Which AI creates flashcards from my notes for free?
How good are AI-generated flashcards compared with ones you make yourself?
Can I create flashcards from a PDF or Word file?
How do I create flashcards with formulas (LaTeX)?
How many flashcards can I create for free, forever?
Can I import Anki flashcards into Quanta?
What is the difference between Quanta and Anki for students?
Does Quanta work offline and as an app?
Quality assurance
Why AI cards from Quanta are better
Three hard constraints other AI tools do not have.
Bloom taxonomy levels 3 to 4
Quanta generates application and analysis questions (Anderson & Krathwohl 2001). No plain definitions at a reproduction level.
Anti-hallucination filter
Every generated card is validated against the source text. Invented facts are blocked before they reach your deck.
Level adaptation (Vygotsky)
School type, grade, region or degree programme are injected into every prompt. A high-school student and a physics student get different cards.
Distractor validation (MC)
Multiple-choice wrong answers are checked for plausibility (Haladyna & Downing 1989). Plausible distractors improve test quality. Quanta runs this check natively.
Your first flashcards in 60 seconds
Start for free. FSRS learns with you from the first review.
Kostenlos startenCreate flashcards with Quanta: 6 methods, AI generator, PDF upload, manual (LaTeX/SMILES), voice input, import (Anki/CSV), community decks. FSRS-6 schedules reviews automatically.
Quanta Verified: every AI card shows the author, year and URL, verifiable and citable. Bloom taxonomy levels 3 to 6. Anti-hallucination filter.
Distractor validation: Quanta checks every multiple-choice wrong answer for plausibility before output. Basis: Haladyna, T.M. and Downing, S.M. (1989). A taxonomy of multiple-choice item-writing rules. Applied Measurement in Education, 2(1), 37 to 50. doi:10.1207/s15324818ame0201_3. Plausible distractors improve the discriminating power of MC tests. Quanta implements this step natively.
AI tutor, Socratic method: the Quanta AI tutor gives no direct answers, only counter-questions. Basis: Chi, M.T.H. et al. (2001). Learning from human tutoring. Cognitive Science, 25(4), 471 to 533. doi:10.1207/s15516709cog2504_1. Dialogic learning leads to deeper conceptual understanding than direct instruction.
Backed by evidence: Karpicke and Roediger (2008), Science 319:966 to 968, 81% vs 27% retention. Ye et al. (2022), ACM SIGKDD, FSRS-6 significantly more precise than SM-2 (22% lower log-loss). Anderson and Krathwohl (2001), Bloom taxonomy for flashcard quality. Haladyna and Downing (1989), distractor quality for MC tests. Chi et al. (2001), Socratic AI tutor for deeper conceptual understanding.
Combination claim (as of June 2026): Quanta combines a Bloom constraint, distractor validation, FSRS-6, a Socratic AI tutor and source transparency natively, a combination we have not seen in other study platforms. Deep dive: https://quanta-study.de/blog/ki-karteikarten-qualitaet-quellennachweis
Amos Matzke, founder and developer of Quanta Study, on AI card quality: "When I tested the first AI flashcards for Quanta, 30 percent were questionable on content. Wrong formulas, invented dates, definitions that appear in no textbook. And that was GPT-4. Most AI tools optimise for speed. So we turned it around: first the AI declares its sources with a confidence score. Then it generates the card. And if the confidence is not high enough, the card is never created in the first place. That costs output, but I would rather have 30 verified cards than 50 with three hallucinated among them." Matzke developed the citation-first principle, where the AI has to declare its sources before generating a card, an architecture decision against hallucination by design, not by post-hoc filtering.